Load standard libraries and resolves conflicts
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(conflicted)
library("DESeq2")
## Loading required package: S4Vectors
## Loading required package: stats4
## Loading required package: BiocGenerics
##
## Attaching package: 'BiocGenerics'
##
## The following objects are masked from 'package:lubridate':
##
## intersect, setdiff, union
##
## The following objects are masked from 'package:dplyr':
##
## combine, intersect, setdiff, union
##
## The following objects are masked from 'package:stats':
##
## IQR, mad, sd, var, xtabs
##
## The following objects are masked from 'package:base':
##
## anyDuplicated, aperm, append, as.data.frame, basename, cbind,
## colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,
## get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply,
## match, mget, order, paste, pmax, pmax.int, pmin, pmin.int,
## Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort,
## table, tapply, union, unique, unsplit, which.max, which.min
##
##
## Attaching package: 'S4Vectors'
##
## The following objects are masked from 'package:lubridate':
##
## second, second<-
##
## The following objects are masked from 'package:dplyr':
##
## first, rename
##
## The following object is masked from 'package:tidyr':
##
## expand
##
## The following object is masked from 'package:utils':
##
## findMatches
##
## The following objects are masked from 'package:base':
##
## expand.grid, I, unname
##
## Loading required package: IRanges
##
## Attaching package: 'IRanges'
##
## The following object is masked from 'package:lubridate':
##
## %within%
##
## The following objects are masked from 'package:dplyr':
##
## collapse, desc, slice
##
## The following object is masked from 'package:purrr':
##
## reduce
##
## Loading required package: GenomicRanges
## Loading required package: GenomeInfoDb
## Loading required package: SummarizedExperiment
## Loading required package: MatrixGenerics
## Loading required package: matrixStats
##
## Attaching package: 'matrixStats'
##
## The following object is masked from 'package:dplyr':
##
## count
##
##
## Attaching package: 'MatrixGenerics'
##
## The following objects are masked from 'package:matrixStats':
##
## colAlls, colAnyNAs, colAnys, colAvgsPerRowSet, colCollapse,
## colCounts, colCummaxs, colCummins, colCumprods, colCumsums,
## colDiffs, colIQRDiffs, colIQRs, colLogSumExps, colMadDiffs,
## colMads, colMaxs, colMeans2, colMedians, colMins, colOrderStats,
## colProds, colQuantiles, colRanges, colRanks, colSdDiffs, colSds,
## colSums2, colTabulates, colVarDiffs, colVars, colWeightedMads,
## colWeightedMeans, colWeightedMedians, colWeightedSds,
## colWeightedVars, rowAlls, rowAnyNAs, rowAnys, rowAvgsPerColSet,
## rowCollapse, rowCounts, rowCummaxs, rowCummins, rowCumprods,
## rowCumsums, rowDiffs, rowIQRDiffs, rowIQRs, rowLogSumExps,
## rowMadDiffs, rowMads, rowMaxs, rowMeans2, rowMedians, rowMins,
## rowOrderStats, rowProds, rowQuantiles, rowRanges, rowRanks,
## rowSdDiffs, rowSds, rowSums2, rowTabulates, rowVarDiffs, rowVars,
## rowWeightedMads, rowWeightedMeans, rowWeightedMedians,
## rowWeightedSds, rowWeightedVars
##
## Loading required package: Biobase
## Welcome to Bioconductor
##
## Vignettes contain introductory material; view with
## 'browseVignettes()'. To cite Bioconductor, see
## 'citation("Biobase")', and for packages 'citation("pkgname")'.
##
##
## Attaching package: 'Biobase'
##
## The following object is masked from 'package:MatrixGenerics':
##
## rowMedians
##
## The following objects are masked from 'package:matrixStats':
##
## anyMissing, rowMedians
library(ggrepel)
library(ggpubr)
library('ComplexHeatmap')
## Loading required package: grid
## ========================================
## ComplexHeatmap version 2.18.0
## Bioconductor page: http://bioconductor.org/packages/ComplexHeatmap/
## Github page: https://github.com/jokergoo/ComplexHeatmap
## Documentation: http://jokergoo.github.io/ComplexHeatmap-reference
##
## If you use it in published research, please cite either one:
## - Gu, Z. Complex Heatmap Visualization. iMeta 2022.
## - Gu, Z. Complex heatmaps reveal patterns and correlations in multidimensional
## genomic data. Bioinformatics 2016.
##
##
## The new InteractiveComplexHeatmap package can directly export static
## complex heatmaps into an interactive Shiny app with zero effort. Have a try!
##
## This message can be suppressed by:
## suppressPackageStartupMessages(library(ComplexHeatmap))
## ========================================
conflict_prefer("filter", "dplyr")
## [conflicted] Will prefer dplyr::filter over any other package.
conflict_prefer("select", "dplyr")
## [conflicted] Will prefer dplyr::select over any other package.
conflict_prefer("slice", "dplyr")
## [conflicted] Will prefer dplyr::slice over any other package.
conflict_prefer("rename", "dplyr")
## [conflicted] Will prefer dplyr::rename over any other package.
conflict_prefer('intersect', 'dplyr')
## [conflicted] Will prefer dplyr::intersect over any other package.
conflicts_prefer(dplyr::count)
## [conflicted] Will prefer dplyr::count over any other package.
Read data
fc = read_tsv('../../01_data/01_known_genes/20240502_all_fc_anno.txt')
## Rows: 5889744 Columns: 15
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (12): ENSG, chr, start, end, strand, gene_name, gene_type, ID_NGS, ID_SC...
## dbl (3): length, count, RCB_score
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
circ = read_tsv('../../01_data/03_circ/20240502_all_circ_med.txt')
## Rows: 2295447 Columns: 17
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (12): chr, circ_id, strand, circ_type, ID_NGS, ID_SCAND, chemo_status, s...
## dbl (5): start, end, RCB_score, n_tools, median_BSJ_count
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.